Análisis de modelos SOM - Frecuencia datos de entrada: dia

Modelo

• ID: 10
• Descripción:
• Frecuencia: dia
• Variables: fecha_cnt, tmax, tmin, precip, longitud, latitud, altitud
• Dimensiones del mapa: 5,5
• Iteraciones: 10000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-010.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 1065343 objects.
Mean distance to the closest unit in the map: 1.193.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_dia_2k.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt          tmax       
 Length:1065343     Length:1065343     Min.   :  1.0   Min.   :-196.0  
 Class :character   Class :character   1st Qu.: 91.0   1st Qu.: 144.0  
 Mode  :character   Mode  :character   Median :183.0   Median : 201.0  
                                       Mean   :182.8   Mean   : 201.5  
                                       3rd Qu.:274.0   3rd Qu.: 263.0  
                                       Max.   :366.0   Max.   : 469.0  
      tmin             precip            nevada    prof_nieve       
 Min.   :-252.00   Min.   :   0.00   Min.   :0   Min.   :   0.0000  
 1st Qu.:  47.00   1st Qu.:   0.00   1st Qu.:0   1st Qu.:   0.0000  
 Median : 100.00   Median :   0.00   Median :0   Median :   0.0000  
 Mean   :  97.54   Mean   :  17.05   Mean   :0   Mean   :   0.6185  
 3rd Qu.: 153.00   3rd Qu.:   2.00   3rd Qu.:0   3rd Qu.:   0.0000  
 Max.   : 332.00   Max.   :3361.00   Max.   :0   Max.   :1240.0000  
    longitud        latitud           altitud    
 Min.   :27.82   Min.   :-17.889   Min.   :   1  
 1st Qu.:39.47   1st Qu.: -4.850   1st Qu.:  47  
 Median :41.29   Median : -1.411   Median : 287  
 Mean   :40.10   Mean   : -2.391   Mean   : 486  
 3rd Qu.:42.22   3rd Qu.:  1.296   3rd Qu.: 691  
 Max.   :43.57   Max.   :  4.216   Max.   :2535  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

    1     2     3     4     5     6     7     8     9    10    11    12    13 
 7724 61066 71660 46008 22211 56906 45197 39247 52210 15126 25347 46495 55161 
   14    15    16    17    18    19    20    21    22    23    24    25 
 9567  1463 51356 59631 58281 42821 30202 93369 47194 27491 51200 48410 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "precip", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

      fecha_cnt       tmax       tmin       precip  longitud   latitud
[1,] 0.01605063 -0.8290019 -0.8768082  0.293938370 0.5649890 0.4146627
[2,] 0.77455275  0.3849234  0.3626317 -0.001570071 0.1797045 0.1932196
         altitud
[1,]  0.46180241
[2,] -0.01398282

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   latitud   altitud      tmax    precip      tmin fecha_cnt 
0.9517478 0.9247384 0.9158391 0.9074087 0.9018573 0.8971768 0.8915602 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax          tmin           precip            nevada 
 Min.   :  1.0   Min.   :-32   Min.   :-75.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:208   1st Qu.:145.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :234   Median :172.0   Median :  0.000   Median :0  
 Mean   :180.8   Mean   :229   Mean   :164.4   Mean   :  4.615   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:262   3rd Qu.:201.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429   Max.   :322.0   Max.   :361.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.06   Mean   : 384.6  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax             tmin             precip      
 Min.   :  1.0   Min.   :-196.0   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 92.0   1st Qu.: 142.0   1st Qu.:  44.00   1st Qu.:  0.00  
 Median :183.0   Median : 197.0   Median :  94.00   Median :  0.00  
 Mean   :182.8   Mean   : 199.8   Mean   :  93.23   Mean   : 16.62  
 3rd Qu.:274.0   3rd Qu.: 263.0   3rd Qu.: 146.00   3rd Qu.:  2.00  
 Max.   :366.0   Max.   : 469.0   Max.   : 332.00   Max.   :633.00  
     nevada    prof_nieve           longitud        latitud       
 Min.   :0   Min.   :   0.0000   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:   0.0000   1st Qu.:39.95   1st Qu.: -4.010  
 Median :0   Median :   0.0000   Median :41.39   Median : -1.117  
 Mean   :0   Mean   :   0.6556   Mean   :40.86   Mean   : -1.509  
 3rd Qu.:0   3rd Qu.:   0.0000   3rd Qu.:42.24   3rd Qu.:  1.366  
 Max.   :0   Max.   :1240.0000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  59.0  
 Median : 336.0  
 Mean   : 492.4  
 3rd Qu.: 704.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :  3.0   Min.   :-63.0   Min.   :-133.00   Min.   : 622.0   Min.   :0  
 1st Qu.:110.0   1st Qu.:106.0   1st Qu.:  55.00   1st Qu.: 683.0   1st Qu.:0  
 Median :272.0   Median :148.0   Median : 102.00   Median : 776.0   Median :0  
 Mean   :219.1   Mean   :146.1   Mean   :  92.28   Mean   : 859.2   Mean   :0  
 3rd Qu.:306.5   3rd Qu.:195.0   3rd Qu.: 138.00   3rd Qu.: 934.5   3rd Qu.:0  
 Max.   :362.0   Max.   :332.0   Max.   : 240.00   Max.   :3361.0   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -1.9623   1st Qu.:  44.0  
 Median :  0.000   Median :41.57   Median :  0.8856   Median : 247.0  
 Mean   :  2.595   Mean   :40.75   Mean   : -0.7467   Mean   : 587.5  
 3rd Qu.:  0.000   3rd Qu.:42.27   3rd Qu.:  2.1053   3rd Qu.: 852.0  
 Max.   :820.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax          tmin           precip            nevada 
 Min.   :  1.0   Min.   :-32   Min.   :-75.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:208   1st Qu.:145.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :234   Median :172.0   Median :  0.000   Median :0  
 Mean   :180.8   Mean   :229   Mean   :164.4   Mean   :  4.615   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:262   3rd Qu.:201.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429   Max.   :322.0   Max.   :361.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.06   Mean   : 384.6  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax           tmin             precip           nevada 
 Min.   :  1.0   Min.   :-116   Min.   :-240.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 91.0   1st Qu.: 150   1st Qu.:  50.00   1st Qu.:  0.00   1st Qu.:0  
 Median :183.0   Median : 204   Median : 100.00   Median :  0.00   Median :0  
 Mean   :182.7   Mean   : 208   Mean   :  98.87   Mean   : 16.25   Mean   :0  
 3rd Qu.:274.0   3rd Qu.: 268   3rd Qu.: 150.00   3rd Qu.:  2.00   3rd Qu.:0  
 Max.   :366.0   Max.   : 469   Max.   : 332.00   Max.   :633.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :   0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:   0.0000   1st Qu.:39.85   1st Qu.: -4.488   1st Qu.:  52.0  
 Median :   0.0000   Median :41.31   Median : -1.293   Median : 261.0  
 Mean   :   0.1054   Mean   :40.77   Mean   : -1.666   Mean   : 376.8  
 3rd Qu.:   0.0000   3rd Qu.:42.14   3rd Qu.:  1.331   3rd Qu.: 656.0  
 Max.   :1240.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin             precip      
 Min.   :  1.0   Min.   :-196.00   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 93.0   1st Qu.:  26.00   1st Qu.: -35.00   1st Qu.:  0.00  
 Median :186.0   Median :  80.00   Median :  13.00   Median :  0.00  
 Mean   :185.3   Mean   :  82.05   Mean   :  11.88   Mean   : 22.03  
 3rd Qu.:278.0   3rd Qu.: 141.00   3rd Qu.:  64.00   3rd Qu.: 17.00  
 Max.   :366.0   Max.   : 277.00   Max.   : 188.00   Max.   :343.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.35   Min.   :-4.6800  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.586   Mean   :42.25   Mean   : 0.7616  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1199.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   : 890  
 1st Qu.:1971  
 Median :2230  
 Mean   :2159  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :  3.0   Min.   :-63.0   Min.   :-133.00   Min.   : 622.0   Min.   :0  
 1st Qu.:110.0   1st Qu.:106.0   1st Qu.:  55.00   1st Qu.: 683.0   1st Qu.:0  
 Median :272.0   Median :148.0   Median : 102.00   Median : 776.0   Median :0  
 Mean   :219.1   Mean   :146.1   Mean   :  92.28   Mean   : 859.2   Mean   :0  
 3rd Qu.:306.5   3rd Qu.:195.0   3rd Qu.: 138.00   3rd Qu.: 934.5   3rd Qu.:0  
 Max.   :362.0   Max.   :332.0   Max.   : 240.00   Max.   :3361.0   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -1.9623   1st Qu.:  44.0  
 Median :  0.000   Median :41.57   Median :  0.8856   Median : 247.0  
 Mean   :  2.595   Mean   :40.75   Mean   : -0.7467   Mean   : 587.5  
 3rd Qu.:  0.000   3rd Qu.:42.27   3rd Qu.:  2.1053   3rd Qu.: 852.0  
 Max.   :820.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax          tmin           precip            nevada 
 Min.   :  1.0   Min.   :-32   Min.   :-75.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:208   1st Qu.:145.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :234   Median :172.0   Median :  0.000   Median :0  
 Mean   :180.8   Mean   :229   Mean   :164.4   Mean   :  4.615   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:262   3rd Qu.:201.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429   Max.   :322.0   Max.   :361.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.06   Mean   : 384.6  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :  1.0   Min.   :-65.0   Min.   :-240.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 91.0   1st Qu.:150.0   1st Qu.:  50.00   1st Qu.:  0.00   1st Qu.:0  
 Median :183.0   Median :204.0   Median : 100.00   Median :  0.00   Median :0  
 Mean   :182.5   Mean   :208.6   Mean   :  99.03   Mean   : 12.39   Mean   :0  
 3rd Qu.:273.0   3rd Qu.:268.0   3rd Qu.: 150.00   3rd Qu.:  1.00   3rd Qu.:0  
 Max.   :366.0   Max.   :469.0   Max.   : 332.00   Max.   :297.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :0.00e+00   Min.   :28.95   Min.   :-13.600   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:39.85   1st Qu.: -4.488   1st Qu.:  52.0  
 Median :0.00e+00   Median :41.31   Median : -1.293   Median : 261.0  
 Mean   :7.28e-02   Mean   :40.76   Mean   : -1.668   Mean   : 374.4  
 3rd Qu.:0.00e+00   3rd Qu.:42.12   3rd Qu.:  1.331   3rd Qu.: 639.0  
 Max.   :1.24e+03   Max.   :43.57   Max.   :  4.216   Max.   :2451.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin             precip      
 Min.   :  1.0   Min.   :-196.00   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 93.0   1st Qu.:  26.00   1st Qu.: -35.00   1st Qu.:  0.00  
 Median :186.0   Median :  80.00   Median :  13.00   Median :  0.00  
 Mean   :185.3   Mean   :  82.05   Mean   :  11.88   Mean   : 22.03  
 3rd Qu.:278.0   3rd Qu.: 141.00   3rd Qu.:  64.00   3rd Qu.: 17.00  
 Max.   :366.0   Max.   : 277.00   Max.   : 188.00   Max.   :343.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.35   Min.   :-4.6800  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.586   Mean   :42.25   Mean   : 0.7616  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1199.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   : 890  
 1st Qu.:1971  
 Median :2230  
 Mean   :2159  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax             tmin             precip          nevada 
 Min.   :  1.0   Min.   :-116.0   Min.   :-143.00   Min.   :259.0   Min.   :0  
 1st Qu.: 95.0   1st Qu.: 102.0   1st Qu.:  48.00   1st Qu.:318.0   1st Qu.:0  
 Median :221.0   Median : 145.0   Median :  90.00   Median :367.0   Median :0  
 Mean   :199.2   Mean   : 145.6   Mean   :  83.22   Mean   :389.2   Mean   :0  
 3rd Qu.:304.0   3rd Qu.: 191.0   3rd Qu.: 126.00   3rd Qu.:442.0   3rd Qu.:0  
 Max.   :366.0   Max.   : 369.0   Max.   : 254.00   Max.   :633.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -4.010   1st Qu.:  69.0  
 Median :  0.000   Median :41.98   Median :  0.595   Median : 316.0  
 Mean   :  3.257   Mean   :41.21   Mean   : -1.484   Mean   : 611.6  
 3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.778   3rd Qu.: 852.0  
 Max.   :899.000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :  3.0   Min.   :-63.0   Min.   :-133.00   Min.   : 622.0   Min.   :0  
 1st Qu.:110.0   1st Qu.:106.0   1st Qu.:  55.00   1st Qu.: 683.0   1st Qu.:0  
 Median :272.0   Median :148.0   Median : 102.00   Median : 776.0   Median :0  
 Mean   :219.1   Mean   :146.1   Mean   :  92.28   Mean   : 859.2   Mean   :0  
 3rd Qu.:306.5   3rd Qu.:195.0   3rd Qu.: 138.00   3rd Qu.: 934.5   3rd Qu.:0  
 Max.   :362.0   Max.   :332.0   Max.   : 240.00   Max.   :3361.0   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -1.9623   1st Qu.:  44.0  
 Median :  0.000   Median :41.57   Median :  0.8856   Median : 247.0  
 Mean   :  2.595   Mean   :40.75   Mean   : -0.7467   Mean   : 587.5  
 3rd Qu.:  0.000   3rd Qu.:42.27   3rd Qu.:  2.1053   3rd Qu.: 852.0  
 Max.   :820.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax          tmin           precip            nevada 
 Min.   :  1.0   Min.   :-32   Min.   :-75.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:208   1st Qu.:145.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :234   Median :172.0   Median :  0.000   Median :0  
 Mean   :180.8   Mean   :229   Mean   :164.4   Mean   :  4.615   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:262   3rd Qu.:201.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429   Max.   :322.0   Max.   :361.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.06   Mean   : 384.6  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   :  1.00   Min.   :-44.0   Min.   :-185.00   Min.   :  0.00  
 1st Qu.: 40.00   1st Qu.:131.0   1st Qu.:  30.00   1st Qu.:  0.00  
 Median : 79.00   Median :169.0   Median :  67.00   Median :  0.00  
 Mean   : 84.96   Mean   :168.8   Mean   :  64.56   Mean   : 21.18  
 3rd Qu.:119.00   3rd Qu.:208.0   3rd Qu.: 102.00   3rd Qu.:  9.00  
 Max.   :366.00   Max.   :379.0   Max.   : 253.00   Max.   :297.00  
     nevada    prof_nieve           longitud        latitud       
 Min.   :0   Min.   :   0.0000   Min.   :28.95   Min.   :-13.600  
 1st Qu.:0   1st Qu.:   0.0000   1st Qu.:39.95   1st Qu.: -4.127  
 Median :0   Median :   0.0000   Median :41.34   Median : -1.229  
 Mean   :0   Mean   :   0.1304   Mean   :40.83   Mean   : -1.572  
 3rd Qu.:0   3rd Qu.:   0.0000   3rd Qu.:42.14   3rd Qu.:  1.363  
 Max.   :0   Max.   :1209.0000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  53.0  
 Median : 261.0  
 Mean   : 377.9  
 3rd Qu.: 656.0  
 Max.   :2451.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin             precip      
 Min.   :  1.0   Min.   :-196.00   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 93.0   1st Qu.:  26.00   1st Qu.: -35.00   1st Qu.:  0.00  
 Median :186.0   Median :  80.00   Median :  13.00   Median :  0.00  
 Mean   :185.3   Mean   :  82.05   Mean   :  11.88   Mean   : 22.03  
 3rd Qu.:278.0   3rd Qu.: 141.00   3rd Qu.:  64.00   3rd Qu.: 17.00  
 Max.   :366.0   Max.   : 277.00   Max.   : 188.00   Max.   :343.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.35   Min.   :-4.6800  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.586   Mean   :42.25   Mean   : 0.7616  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1199.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   : 890  
 1st Qu.:1971  
 Median :2230  
 Mean   :2159  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 58.0   Min.   :-65.0   Min.   :-240.0   Min.   :  0.00   Min.   :0  
 1st Qu.:205.0   1st Qu.:181.0   1st Qu.:  82.0   1st Qu.:  0.00   1st Qu.:0  
 Median :257.0   Median :250.0   Median : 135.0   Median :  0.00   Median :0  
 Mean   :257.1   Mean   :239.1   Mean   : 125.4   Mean   :  5.67   Mean   :0  
 3rd Qu.:312.0   3rd Qu.:300.0   3rd Qu.: 176.0   3rd Qu.:  0.00   3rd Qu.:0  
 Max.   :366.0   Max.   :469.0   Max.   : 332.0   Max.   :222.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :0.00e+00   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:39.49   1st Qu.:-4.488   1st Qu.:  52.0  
 Median :0.00e+00   Median :41.29   Median :-1.411   Median : 258.0  
 Mean   :2.88e-02   Mean   :40.71   Mean   :-1.742   Mean   : 371.6  
 3rd Qu.:0.00e+00   3rd Qu.:42.11   3rd Qu.: 1.201   3rd Qu.: 639.0  
 Max.   :1.24e+03   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax             tmin             precip          nevada 
 Min.   :  1.0   Min.   :-116.0   Min.   :-143.00   Min.   :259.0   Min.   :0  
 1st Qu.: 95.0   1st Qu.: 102.0   1st Qu.:  48.00   1st Qu.:318.0   1st Qu.:0  
 Median :221.0   Median : 145.0   Median :  90.00   Median :367.0   Median :0  
 Mean   :199.2   Mean   : 145.6   Mean   :  83.22   Mean   :389.2   Mean   :0  
 3rd Qu.:304.0   3rd Qu.: 191.0   3rd Qu.: 126.00   3rd Qu.:442.0   3rd Qu.:0  
 Max.   :366.0   Max.   : 369.0   Max.   : 254.00   Max.   :633.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -4.010   1st Qu.:  69.0  
 Median :  0.000   Median :41.98   Median :  0.595   Median : 316.0  
 Mean   :  3.257   Mean   :41.21   Mean   : -1.484   Mean   : 611.6  
 3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.778   3rd Qu.: 852.0  
 Max.   :899.000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :  3.0   Min.   :-63.0   Min.   :-133.00   Min.   : 622.0   Min.   :0  
 1st Qu.:110.0   1st Qu.:106.0   1st Qu.:  55.00   1st Qu.: 683.0   1st Qu.:0  
 Median :272.0   Median :148.0   Median : 102.00   Median : 776.0   Median :0  
 Mean   :219.1   Mean   :146.1   Mean   :  92.28   Mean   : 859.2   Mean   :0  
 3rd Qu.:306.5   3rd Qu.:195.0   3rd Qu.: 138.00   3rd Qu.: 934.5   3rd Qu.:0  
 Max.   :362.0   Max.   :332.0   Max.   : 240.00   Max.   :3361.0   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -1.9623   1st Qu.:  44.0  
 Median :  0.000   Median :41.57   Median :  0.8856   Median : 247.0  
 Mean   :  2.595   Mean   :40.75   Mean   : -0.7467   Mean   : 587.5  
 3rd Qu.:  0.000   3rd Qu.:42.27   3rd Qu.:  2.1053   3rd Qu.: 852.0  
 Max.   :820.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin            precip            nevada 
 Min.   :  1.0   Min.   :-32.0   Min.   :-75.00   Min.   :  0.000   Min.   :0  
 1st Qu.: 91.0   1st Qu.:100.0   1st Qu.: 27.00   1st Qu.:  0.000   1st Qu.:0  
 Median :180.0   Median :143.0   Median : 65.00   Median :  0.000   Median :0  
 Mean   :181.2   Mean   :144.6   Mean   : 68.22   Mean   :  6.009   Mean   :0  
 3rd Qu.:271.0   3rd Qu.:191.0   3rd Qu.:109.00   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :290.0   Max.   :206.00   Max.   :361.000   Max.   :0  
   prof_nieve    longitud        latitud         altitud    
 Min.   :0    Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.:0    1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median :0    Median :28.31   Median :-16.5   Median :2371  
 Mean   :0    Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.:0    3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :0    Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   :  1.00   Min.   :-44.0   Min.   :-185.00   Min.   :  0.00  
 1st Qu.: 40.00   1st Qu.:131.0   1st Qu.:  30.00   1st Qu.:  0.00  
 Median : 79.00   Median :169.0   Median :  67.00   Median :  0.00  
 Mean   : 84.96   Mean   :168.8   Mean   :  64.56   Mean   : 21.18  
 3rd Qu.:119.00   3rd Qu.:208.0   3rd Qu.: 102.00   3rd Qu.:  9.00  
 Max.   :366.00   Max.   :379.0   Max.   : 253.00   Max.   :297.00  
     nevada    prof_nieve           longitud        latitud       
 Min.   :0   Min.   :   0.0000   Min.   :28.95   Min.   :-13.600  
 1st Qu.:0   1st Qu.:   0.0000   1st Qu.:39.95   1st Qu.: -4.127  
 Median :0   Median :   0.0000   Median :41.34   Median : -1.229  
 Mean   :0   Mean   :   0.1304   Mean   :40.83   Mean   : -1.572  
 3rd Qu.:0   3rd Qu.:   0.0000   3rd Qu.:42.14   3rd Qu.:  1.363  
 Max.   :0   Max.   :1209.0000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  53.0  
 Median : 261.0  
 Mean   : 377.9  
 3rd Qu.: 656.0  
 Max.   :2451.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax              tmin             precip      
 Min.   :  1.0   Min.   :-196.00   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 93.0   1st Qu.:  26.00   1st Qu.: -35.00   1st Qu.:  0.00  
 Median :186.0   Median :  80.00   Median :  13.00   Median :  0.00  
 Mean   :185.3   Mean   :  82.05   Mean   :  11.88   Mean   : 22.03  
 3rd Qu.:278.0   3rd Qu.: 141.00   3rd Qu.:  64.00   3rd Qu.: 17.00  
 Max.   :366.0   Max.   : 277.00   Max.   : 188.00   Max.   :343.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.35   Min.   :-4.6800  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.586   Mean   :42.25   Mean   : 0.7616  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1199.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   : 890  
 1st Qu.:1971  
 Median :2230  
 Mean   :2159  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  1.0   Min.   :107.0   Min.   : 38.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:216.0   1st Qu.:156.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :239.0   Median :178.0   Median :  0.000   Median :0  
 Mean   :180.8   Mean   :240.5   Mean   :177.5   Mean   :  4.426   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:265.0   3rd Qu.:205.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429.0   Max.   :322.0   Max.   :336.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud     
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-17.75   1st Qu.: 25.0  
 Median :0    Median :28.46   Median :-16.33   Median : 33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.00   Mean   :114.9  
 3rd Qu.:0    3rd Qu.:28.63   3rd Qu.:-13.86   3rd Qu.: 64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :189.0   Min.   :-65.0   Min.   :-240.00   Min.   :  0.00   Min.   :0  
 1st Qu.:311.0   1st Qu.:117.0   1st Qu.:  19.00   1st Qu.:  0.00   1st Qu.:0  
 Median :331.0   Median :151.0   Median :  54.00   Median :  0.00   Median :0  
 Mean   :327.9   Mean   :148.2   Mean   :  51.72   Mean   :  9.32   Mean   :0  
 3rd Qu.:349.0   3rd Qu.:180.0   3rd Qu.:  85.00   3rd Qu.:  2.00   3rd Qu.:0  
 Max.   :366.0   Max.   :320.0   Max.   : 204.00   Max.   :222.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :0.00e+00   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:40.07   1st Qu.:-4.767   1st Qu.:  79.0  
 Median :0.00e+00   Median :41.38   Median :-1.885   Median : 370.0  
 Mean   :8.15e-02   Mean   :40.80   Mean   :-1.938   Mean   : 423.1  
 3rd Qu.:0.00e+00   3rd Qu.:42.18   3rd Qu.: 1.168   3rd Qu.: 687.0  
 Max.   :1.24e+03   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 58.0   Min.   :138.0   Min.   :-16.0   Min.   :  0.000   Min.   :0  
 1st Qu.:188.0   1st Qu.:247.0   1st Qu.:131.0   1st Qu.:  0.000   1st Qu.:0  
 Median :223.0   Median :283.0   Median :161.0   Median :  0.000   Median :0  
 Mean   :223.7   Mean   :281.9   Mean   :160.1   Mean   :  3.951   Mean   :0  
 3rd Qu.:259.0   3rd Qu.:315.0   3rd Qu.:190.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :365.0   Max.   :469.0   Max.   :332.0   Max.   :180.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :   0.000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:   0.000   1st Qu.:39.49   1st Qu.:-4.127   1st Qu.:  43.3  
 Median :   0.000   Median :41.19   Median :-1.229   Median : 192.0  
 Mean   :   0.004   Mean   :40.66   Mean   :-1.650   Mean   : 347.4  
 3rd Qu.:   0.000   3rd Qu.:42.08   3rd Qu.: 1.331   3rd Qu.: 617.0  
 Max.   :1039.000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax             tmin             precip          nevada 
 Min.   :  1.0   Min.   :-116.0   Min.   :-143.00   Min.   :259.0   Min.   :0  
 1st Qu.: 95.0   1st Qu.: 102.0   1st Qu.:  48.00   1st Qu.:318.0   1st Qu.:0  
 Median :221.0   Median : 145.0   Median :  90.00   Median :367.0   Median :0  
 Mean   :199.2   Mean   : 145.6   Mean   :  83.22   Mean   :389.2   Mean   :0  
 3rd Qu.:304.0   3rd Qu.: 191.0   3rd Qu.: 126.00   3rd Qu.:442.0   3rd Qu.:0  
 Max.   :366.0   Max.   : 369.0   Max.   : 254.00   Max.   :633.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -4.010   1st Qu.:  69.0  
 Median :  0.000   Median :41.98   Median :  0.595   Median : 316.0  
 Mean   :  3.257   Mean   :41.21   Mean   : -1.484   Mean   : 611.6  
 3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.778   3rd Qu.: 852.0  
 Max.   :899.000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :  3.0   Min.   :-63.0   Min.   :-133.00   Min.   : 622.0   Min.   :0  
 1st Qu.:110.0   1st Qu.:106.0   1st Qu.:  55.00   1st Qu.: 683.0   1st Qu.:0  
 Median :272.0   Median :148.0   Median : 102.00   Median : 776.0   Median :0  
 Mean   :219.1   Mean   :146.1   Mean   :  92.28   Mean   : 859.2   Mean   :0  
 3rd Qu.:306.5   3rd Qu.:195.0   3rd Qu.: 138.00   3rd Qu.: 934.5   3rd Qu.:0  
 Max.   :362.0   Max.   :332.0   Max.   : 240.00   Max.   :3361.0   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -1.9623   1st Qu.:  44.0  
 Median :  0.000   Median :41.57   Median :  0.8856   Median : 247.0  
 Mean   :  2.595   Mean   :40.75   Mean   : -0.7467   Mean   : 587.5  
 3rd Qu.:  0.000   3rd Qu.:42.27   3rd Qu.:  2.1053   3rd Qu.: 852.0  
 Max.   :820.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin            precip            nevada 
 Min.   :  1.0   Min.   :-32.0   Min.   :-75.00   Min.   :  0.000   Min.   :0  
 1st Qu.: 91.0   1st Qu.:100.0   1st Qu.: 27.00   1st Qu.:  0.000   1st Qu.:0  
 Median :180.0   Median :143.0   Median : 65.00   Median :  0.000   Median :0  
 Mean   :181.2   Mean   :144.6   Mean   : 68.22   Mean   :  6.009   Mean   :0  
 3rd Qu.:271.0   3rd Qu.:191.0   3rd Qu.:109.00   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :290.0   Max.   :206.00   Max.   :361.000   Max.   :0  
   prof_nieve    longitud        latitud         altitud    
 Min.   :0    Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.:0    1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median :0    Median :28.31   Median :-16.5   Median :2371  
 Mean   :0    Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.:0    3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :0    Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin            precip       
 Min.   :  1.00   Min.   : 37.0   Min.   :-68.00   Min.   :  0.000  
 1st Qu.: 53.00   1st Qu.:159.0   1st Qu.: 56.00   1st Qu.:  0.000  
 Median : 92.00   Median :188.0   Median : 82.00   Median :  0.000  
 Mean   : 88.38   Mean   :190.7   Mean   : 82.77   Mean   :  8.108  
 3rd Qu.:124.00   3rd Qu.:222.0   3rd Qu.:110.00   3rd Qu.:  2.000  
 Max.   :234.00   Max.   :357.0   Max.   :205.00   Max.   :154.000  
     nevada    prof_nieve           longitud        latitud      
 Min.   :0   Min.   :   0.0000   Min.   :35.28   Min.   :-8.624  
 1st Qu.:0   1st Qu.:   0.0000   1st Qu.:39.01   1st Qu.:-4.680  
 Median :0   Median :   0.0000   Median :41.19   Median :-1.008  
 Mean   :0   Mean   :   0.0328   Mean   :40.58   Mean   :-1.543  
 3rd Qu.:0   3rd Qu.:   0.0000   3rd Qu.:42.07   3rd Qu.: 1.384  
 Max.   :0   Max.   :1209.0000   Max.   :43.57   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  33.0  
 Median : 108.0  
 Mean   : 261.7  
 3rd Qu.: 442.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin              precip       
 Min.   :  1.00   Min.   :-44.0   Min.   :-185.000   Min.   :  0.000  
 1st Qu.: 20.00   1st Qu.: 84.0   1st Qu.: -18.000   1st Qu.:  0.000  
 Median : 41.00   Median :110.0   Median :   5.000   Median :  0.000  
 Mean   : 45.43   Mean   :108.2   Mean   :   4.102   Mean   :  9.661  
 3rd Qu.: 65.00   3rd Qu.:135.0   3rd Qu.:  28.000   3rd Qu.:  4.000  
 Max.   :194.00   Max.   :239.0   Max.   : 106.000   Max.   :194.000  
     nevada    prof_nieve           longitud        latitud      
 Min.   :0   Min.   :   0.0000   Min.   :35.89   Min.   :-8.624  
 1st Qu.:0   1st Qu.:   0.0000   1st Qu.:40.70   1st Qu.:-3.789  
 Median :0   Median :   0.0000   Median :41.60   Median :-1.650  
 Mean   :0   Mean   :   0.3771   Mean   :41.33   Mean   :-1.482  
 3rd Qu.:0   3rd Qu.:   0.0000   3rd Qu.:42.14   3rd Qu.: 1.296  
 Max.   :0   Max.   :1021.0000   Max.   :43.57   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.: 515.0  
 Median : 690.0  
 Mean   : 698.5  
 3rd Qu.: 900.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax              tmin             precip      
 Min.   :  1.0   Min.   :-196.00   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 93.0   1st Qu.:  26.00   1st Qu.: -35.00   1st Qu.:  0.00  
 Median :186.0   Median :  80.00   Median :  13.00   Median :  0.00  
 Mean   :185.3   Mean   :  82.05   Mean   :  11.88   Mean   : 22.03  
 3rd Qu.:278.0   3rd Qu.: 141.00   3rd Qu.:  64.00   3rd Qu.: 17.00  
 Max.   :366.0   Max.   : 277.00   Max.   : 188.00   Max.   :343.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.35   Min.   :-4.6800  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.586   Mean   :42.25   Mean   : 0.7616  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1199.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   : 890  
 1st Qu.:1971  
 Median :2230  
 Mean   :2159  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  1.0   Min.   :107.0   Min.   : 38.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:216.0   1st Qu.:156.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :239.0   Median :178.0   Median :  0.000   Median :0  
 Mean   :180.8   Mean   :240.5   Mean   :177.5   Mean   :  4.426   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:265.0   3rd Qu.:205.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429.0   Max.   :322.0   Max.   :336.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud     
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-17.75   1st Qu.: 25.0  
 Median :0    Median :28.46   Median :-16.33   Median : 33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.00   Mean   :114.9  
 3rd Qu.:0    3rd Qu.:28.63   3rd Qu.:-13.86   3rd Qu.: 64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :189.0   Min.   :-65.0   Min.   :-240.00   Min.   :  0.00   Min.   :0  
 1st Qu.:311.0   1st Qu.:117.0   1st Qu.:  19.00   1st Qu.:  0.00   1st Qu.:0  
 Median :331.0   Median :151.0   Median :  54.00   Median :  0.00   Median :0  
 Mean   :327.9   Mean   :148.2   Mean   :  51.72   Mean   :  9.32   Mean   :0  
 3rd Qu.:349.0   3rd Qu.:180.0   3rd Qu.:  85.00   3rd Qu.:  2.00   3rd Qu.:0  
 Max.   :366.0   Max.   :320.0   Max.   : 204.00   Max.   :222.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :0.00e+00   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:40.07   1st Qu.:-4.767   1st Qu.:  79.0  
 Median :0.00e+00   Median :41.38   Median :-1.885   Median : 370.0  
 Mean   :8.15e-02   Mean   :40.80   Mean   :-1.938   Mean   : 423.1  
 3rd Qu.:0.00e+00   3rd Qu.:42.18   3rd Qu.: 1.168   3rd Qu.: 687.0  
 Max.   :1.24e+03   Max.   :43.57   Max.   : 4.216   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   : 58.0   Min.   :138.0   Min.   :-16.0   Min.   :  0.000   Min.   :0  
 1st Qu.:188.0   1st Qu.:247.0   1st Qu.:131.0   1st Qu.:  0.000   1st Qu.:0  
 Median :223.0   Median :283.0   Median :161.0   Median :  0.000   Median :0  
 Mean   :223.7   Mean   :281.9   Mean   :160.1   Mean   :  3.951   Mean   :0  
 3rd Qu.:259.0   3rd Qu.:315.0   3rd Qu.:190.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :365.0   Max.   :469.0   Max.   :332.0   Max.   :180.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   :   0.000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:   0.000   1st Qu.:39.49   1st Qu.:-4.127   1st Qu.:  43.3  
 Median :   0.000   Median :41.19   Median :-1.229   Median : 192.0  
 Mean   :   0.004   Mean   :40.66   Mean   :-1.650   Mean   : 347.4  
 3rd Qu.:   0.000   3rd Qu.:42.08   3rd Qu.: 1.331   3rd Qu.: 617.0  
 Max.   :1039.000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax             tmin             precip          nevada 
 Min.   :  1.0   Min.   :-116.0   Min.   :-143.00   Min.   :259.0   Min.   :0  
 1st Qu.: 95.0   1st Qu.: 102.0   1st Qu.:  48.00   1st Qu.:318.0   1st Qu.:0  
 Median :221.0   Median : 145.0   Median :  90.00   Median :367.0   Median :0  
 Mean   :199.2   Mean   : 145.6   Mean   :  83.22   Mean   :389.2   Mean   :0  
 3rd Qu.:304.0   3rd Qu.: 191.0   3rd Qu.: 126.00   3rd Qu.:442.0   3rd Qu.:0  
 Max.   :366.0   Max.   : 369.0   Max.   : 254.00   Max.   :633.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -4.010   1st Qu.:  69.0  
 Median :  0.000   Median :41.98   Median :  0.595   Median : 316.0  
 Mean   :  3.257   Mean   :41.21   Mean   : -1.484   Mean   : 611.6  
 3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.778   3rd Qu.: 852.0  
 Max.   :899.000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :  3.0   Min.   :-63.0   Min.   :-133.00   Min.   : 622.0   Min.   :0  
 1st Qu.:110.0   1st Qu.:106.0   1st Qu.:  55.00   1st Qu.: 683.0   1st Qu.:0  
 Median :272.0   Median :148.0   Median : 102.00   Median : 776.0   Median :0  
 Mean   :219.1   Mean   :146.1   Mean   :  92.28   Mean   : 859.2   Mean   :0  
 3rd Qu.:306.5   3rd Qu.:195.0   3rd Qu.: 138.00   3rd Qu.: 934.5   3rd Qu.:0  
 Max.   :362.0   Max.   :332.0   Max.   : 240.00   Max.   :3361.0   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -1.9623   1st Qu.:  44.0  
 Median :  0.000   Median :41.57   Median :  0.8856   Median : 247.0  
 Mean   :  2.595   Mean   :40.75   Mean   : -0.7467   Mean   : 587.5  
 3rd Qu.:  0.000   3rd Qu.:42.27   3rd Qu.:  2.1053   3rd Qu.: 852.0  
 Max.   :820.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   :  1.0   Min.   : -9.0   Min.   :-63.00   Min.   : 76.0   Min.   :0  
 1st Qu.: 96.0   1st Qu.:128.0   1st Qu.: 67.00   1st Qu.:138.0   1st Qu.:0  
 Median :159.0   Median :163.0   Median : 97.00   Median :169.0   Median :0  
 Mean   :182.8   Mean   :168.8   Mean   : 96.95   Mean   :176.5   Mean   :0  
 3rd Qu.:287.0   3rd Qu.:205.0   3rd Qu.:128.00   3rd Qu.:212.0   3rd Qu.:0  
 Max.   :366.0   Max.   :379.0   Max.   :253.00   Max.   :297.0   Max.   :0  
   prof_nieve           longitud        latitud           altitud    
 Min.   :   0.0000   Min.   :28.95   Min.   :-13.600   Min.   :   1  
 1st Qu.:   0.0000   1st Qu.:40.80   1st Qu.: -5.498   1st Qu.:  61  
 Median :   0.0000   Median :41.88   Median : -2.039   Median : 261  
 Mean   :   0.2077   Mean   :41.43   Mean   : -2.120   Mean   : 384  
 3rd Qu.:   0.0000   3rd Qu.:42.70   3rd Qu.:  1.363   3rd Qu.: 617  
 Max.   :1001.0000   Max.   :43.57   Max.   :  4.216   Max.   :2451  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)